Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608. 10357v1 Announce Type: cross Abstract: Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards.
arXiv:2608. 10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot.
arXiv:2608. 09967v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to interpret.
arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.
arXiv:2608. 10126v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity.
arXiv:2608. 10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions.
arXiv:2608. 10827v1 Announce Type: cross Abstract: Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence.
arXiv:2608. 11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents.
arXiv:2608. 10897v1 Announce Type: new Abstract: Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders.
arXiv:2608. 10332v1 Announce Type: cross Abstract: Differentiable predictive control (DPC), a self-supervised learning approach for approximating explicit model predictive control (MPC) policies, offers significant computational advantages over online optimization-based MPC.
arXiv:2608. 10526v1 Announce Type: cross Abstract: Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown.
arXiv:2608. 10207v1 Announce Type: new Abstract: Bus bunching degrades service regularity and increases passenger waiting in high-frequency transit.
arXiv:2608. 10362v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive target model decoding steps.
arXiv:2605. 15850v3 Announce Type: replace-cross Abstract: In recent years, generative AI (GenAI) in educational settings has become ubiquitous in university students' daily lives, despite its potential to induce over-reliance, metacognitive disengagement, and diminished learning when used unrestrictedly.
arXiv:2608. 10323v1 Announce Type: new Abstract: Competitive artificial-life systems can rank trained controllers differently under training and ecological evaluation.
arXiv:2605. 16411v3 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling.
arXiv:2511. 19436v2 Announce Type: replace-cross Abstract: Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external supervision.
arXiv:2608. 10402v1 Announce Type: new Abstract: Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume with growing contexts, and finish at highly variable times.
arXiv:2608. 10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints.
arXiv:2608. 10473v1 Announce Type: cross Abstract: Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction.